© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 112314
    Prev
    Next
    INDEX
    Explanations

    What you need or want to know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inium
    -0.11
    lund
    -0.10
     smack
    -0.10
    uin
    -0.10
    Requirements
    -0.10
     Cri
    -0.10
     crem
    -0.10
     ember
    -0.10
     Rue
    -0.10
    aru
    -0.10
    POSITIVE LOGITS
    need
    0.17
     Need
    0.17
     need
    0.15
     WANT
    0.15
     NEED
    0.14
    Need
    0.14
     wanna
    0.12
     needing
    0.12
    _need
    0.12
     Want
    0.11
    Activations Density 0.142%

    No Known Activations